Модельді жалпылау
Related Papers
Learning to Learn to be Right for the Right Reasons
AbstractImproving model generalization on held-out data is one of the core objectives in common- sense reasoning. Recent work has shown that models trained on the dataset with superficial cues tend …...
Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation
AbstractPublic datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train …...
Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model
AbstractIn knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a teacher is considered …...
Less Is Better: Recovering Intended-Feature Subspace to Robustify NLU Models
AbstractDatasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of …...